Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9306578947368421
+      value: 0.9272368421052631
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Jeevesh8/lecun_feather_berts-3](https://huggingface.co/Jeevesh8/lecun_feather_berts-3) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9307
+- accuracy: 0.9272
 
 ## Model description
 
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2453   | None       | 0     |
-| 0.9118   | 0.3334     | 0     |
-| 0.9241   | 0.2338     | 1     |
-| 0.9303   | 0.2100     | 2     |
-| 0.9307   | 0.1972     | 3     |
+| 0.2434   | None       | 0     |
+| 0.9138   | 0.3287     | 0     |
+| 0.9224   | 0.2340     | 1     |
+| 0.9255   | 0.2112     | 2     |
+| 0.9272   | 0.2000     | 3     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc70c7ba23f018371fe1f1e90c89d7b03bcdfc9ec3b9e90a05ff1d9a0b05449
+oid sha256:4149152846863fda5a519965e1af28f712c7756c22dcfe11730ee76bfd44f839
 size 166552